INDEX

Explanations

references to email or messaging systems

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erman

-0.19

bourg

-0.18

opian

-0.15

ache

-0.15

hei

-0.15

ifier

-0.15

undi

-0.14

 spoon

-0.14

borough

-0.14

POSITIVE LOGITS

onas

0.18

ichert

0.18

 chain

0.15

fragistics

0.15

hit

0.15

Ð°Ð»Ð¸Ð·

0.15

ooks

0.14

 rÃ³wn

0.14

 Chain

0.14

 chains

0.14

Activations Density 0.006%

references to email or messaging systems

No Comments

No Known Activations